CN110084789A - A kind of quality evaluating method and calculating equipment of iris image - Google Patents
A kind of quality evaluating method and calculating equipment of iris image Download PDFInfo
- Publication number
- CN110084789A CN110084789A CN201910299773.7A CN201910299773A CN110084789A CN 110084789 A CN110084789 A CN 110084789A CN 201910299773 A CN201910299773 A CN 201910299773A CN 110084789 A CN110084789 A CN 110084789A
- Authority
- CN
- China
- Prior art keywords
- marginal
- iris image
- marginal point
- point
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of quality evaluating method of iris image and calculate equipment.Wherein, the quality evaluating method is comprising steps of extract the hot spot marginal point of iris image；Ellipse fitting is carried out to hot spot marginal point, to obtain the ellipse of at least one fitting；Oval according to fitting calculates fitting parameter；Based on fitting parameter, the quality evaluation result of iris image is determined.In addition, the present invention also discloses calculating equipment and corresponding readable storage medium storing program for executing for executing the above method together.
Description
Technical field
The present invention relates to technical field of image processing, in particular to the quality evaluating method of a kind of iris image and calculating are set
It is standby.
Background technique
Iris is the annular tissue between human eye white sclera and black pupil, contains the most abundant texture letter
Breath.From the appearance point of view, iris is made of many gland nests, fold and pigmented spots etc., it is one of most unique result in human body.As
Important identification feature, iris recognition have many advantages, such as uniqueness, stability, can collectivity and non-infringement property.Thus, rainbow
Film identification technology is the biometrics identification technology that can accurately identify individual, there is huge application prospect.
Iris authentication system is increasingly being used for large-scale application scene, in general, the workflow of iris authentication system
Journey are as follows: first acquire registered images and generate enrollment；Identification image is acquired again generates identification code, it will be in identification code and database
Recognition template is compared, and completes primary identification work.As can be seen that iris image is obtained through entire identifying system, and
In practical application, due to user's individual difference, it is usually present strabismus in iris image video flowing, closes one's eyes and the quality such as fuzzy are paid no attention to
The image thought.If the bad image of quality is carried out iris recognition, it will increase recognition time, cause undesirable user experience,
It also will increase the risk of wrong identification simultaneously.Therefore, either registration phase or cognitive phase, are commented by iris image quality
Valence filters out the iris image met the requirements, is all vital.
The quality evaluating method of existing iris image, such as the rainbow proposed in document " quality evaluation of iris image is studied "
The quality evaluating method of film image, using the high frequency of the operator extraction pupil two sides part Laplacian (LoG) iris image
Energy, the clarity evaluation index of Lai Shengcheng iris image.Research thinks that evaluation index is higher, and iris image is more clear, that is,
Quality is better.But applicant has found under study for action, since high-frequency energy is related to the information content of image itself, for some lines
The more iris image of reason, details, high-frequency energy is also more, even if image definition is inadequate, but calculated clarity is commented
Valence index still can be higher than that those textures are less, clearly iris image.Therefore, in practical applications, Different Individual iris
The difference of the constituent elements such as region fold and pigmented spots can greatly influence the difference of evaluation index.
In view of the foregoing, a kind of quality assessment scheme of the iris image of optimization is needed, Different Individual can be overcome
Influence of the iris difference to quality evaluation.
Summary of the invention
For this purpose, the present invention provides a kind of quality evaluating method of iris image and calculate equipment, with try hard to solve or
At least alleviate at least one existing problem above.
According to an aspect of the present invention, a kind of quality evaluating method of iris image is provided, the method comprising the steps of: mentioned
Take the hot spot marginal point of iris image；Ellipse fitting is carried out to hot spot marginal point, to obtain the ellipse of at least one fitting；According to
The oval of fitting calculates fitting parameter；Based on fitting parameter, the quality evaluation result of iris image is determined.
Optionally, in the method according to the invention, the step of extracting the hot spot marginal point of iris image includes: calculating rainbow
The gradient of film image；According to the counted gradient of institute, the marginal point in iris image is extracted；According to the gray scale of extracted marginal point
Variation, selects candidate marginal from marginal point；According to the coordinate of candidate marginal, glossing up side is screened from candidate marginal
Edge point.
Optionally, in the method according to the invention, according to the counted gradient of institute, the step of the marginal point of iris image is extracted
It suddenly include: the gradient direction for calculating each pixel in iris image；Gradient direction based on pixel, determines the pixel
Greatest gradient；Greatest gradient based on pixel extracts the marginal point of iris image.
Optionally, in the method according to the invention, based on the greatest gradient of pixel, the marginal point of iris image is extracted
If the step of include: pixel gradient value be greater than the pixel greatest gradient, it is determined that the pixel be marginal point；If picture
The gradient value of vegetarian refreshments is not more than the greatest gradient of the pixel, it is determined that the pixel is not marginal point.
Optionally, in the method according to the invention, it according to the grey scale change of extracted marginal point, is selected from marginal point
The step of candidate marginal includes: to calculate the grey scale change of marginal point four direction out；Determine the maximum absolute value of grey scale change
Direction；On the direction of maximum absolute value, candidate marginal is determined from marginal point.
Optionally, in the method according to the invention, it according to the coordinate of candidate marginal, is filtered out from candidate marginal
The step of hot spot marginal point includes: the average value by calculating the coordinate of all candidate marginals, generates center point coordinate；Pass through
The distance value for calculating each candidate marginal and central point generates the average value of all distance values, as apart from mean value；By from time
Selected distance value in marginal point is selected to be not more than the marginal point apart from mean value, to determine new candidate marginal；By calculating newly
The variance of the distance value of candidate marginal, to determine glossing up marginal point.
Optionally, in the method according to the invention, by calculating the variance of the distance value of new candidate marginal, come true
If the step of making hot spot marginal point includes: that variance is less than predetermined value, using new candidate marginal as hot spot marginal point；If
Variance is not less than predetermined value, then to new candidate marginal, repeats above-mentioned generation center point coordinate and apart from mean value and determination
The step of new candidate marginal is with variance is calculated, until the counted variance of institute is less than predetermined value, by identified new candidate
Marginal point is as hot spot marginal point.
Optionally, in the method according to the invention, ellipse fitting is carried out to hot spot marginal point, it is quasi- to obtain at least one
The oval step of conjunction includes: that hot spot marginal point is divided into two hot spots according to the connected relation of hot spot marginal point；By two light
Spot is fitted to ellipse respectively.
Optionally, in the method according to the invention, fitting parameter includes: each elliptical area, eccentricity and two
The distance between ellipse.
Optionally, in the method according to the invention, it is based on fitting parameter, determines the quality evaluation result of iris image
Step include: according to each elliptical area, determine area and；If area and in the first predetermined interval and each elliptical
Eccentricity is in the distance between the second predetermined interval and two ellipses and is in third predetermined interval, it is determined that iris image
For clear image.
Optionally, in the method according to the invention, it is based on fitting parameter, determines the quality evaluation result of iris image
Step further include: if area and being not at the first predetermined interval, it is determined that iris image is the first vague category identifier；If each ellipse
Eccentricity be not at the second predetermined interval, it is determined that iris image be the second vague category identifier；If between two ellipses away from
From being not at third predetermined interval, it is determined that iris image is the first vague category identifier or the second vague category identifier.
Optionally, in the method according to the invention, the first vague category identifier is defocus blur, and second vague category identifier is
Motion blur.
Optionally, it further comprises the steps of: according to the method for the present invention and original iris image is compressed and is filtered.
According to another aspect of the invention, a kind of calculating equipment is provided, comprising: one or more processors；Memory；
And one or more programs, wherein one or more programs store in memory and are configured as being handled by one or more
Device executes, and one or more programs include the instruction for either executing in method as described above method.
In accordance with a further aspect of the present invention, a kind of computer-readable storage medium for storing one or more programs is provided
Matter, one or more programs include instruction, and instruction is when calculating equipment execution, so that calculating equipment executes method as described above
In either method.
The quality assessment scheme of iris image according to the present invention, by extracting the hot spot of iris image and being carried out to it
Analysis, obtains the quality evaluation result about iris image.Since hot spot will not change because of the individual difference of subject,
Therefore the misjudgment introduced due to the iris texture difference of Different Individual can be got rid of according to the solution of the present invention.
Detailed description of the invention
To the accomplishment of the foregoing and related purposes, certain illustrative sides are described herein in conjunction with following description and drawings
Face, these aspects indicate the various modes that can practice principles disclosed herein, and all aspects and its equivalent aspect
It is intended to fall in the range of theme claimed.Read following detailed description in conjunction with the accompanying drawings, the disclosure it is above-mentioned
And other purposes, feature and advantage will be apparent.Throughout the disclosure, identical appended drawing reference generally refers to identical
Component or element.
Fig. 1 shows the schematic diagram of calculating equipment 100 according to some embodiments of the present invention；
Fig. 2A -2C shows the comparison diagram of the iris image of different readabilities according to an embodiment of the invention；
Fig. 3 shows the flow chart of the quality evaluating method 300 of iris image according to some embodiments of the invention；
Fig. 4 A and Fig. 4 B respectively illustrate according to an embodiment of the invention comprising candidate marginal and comprising hot spot side
The iris image of edge point；
Fig. 5 shows the partial schematic diagram according to an embodiment of the invention for fitting elliptical iris image.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 is the block diagram of Example Computing Device 100.In basic configuration 102, calculating equipment 100, which typically comprises, is
System memory 106 and one or more processor 104.Memory bus 108 can be used for storing in processor 104 and system
Communication between device 106.
Depending on desired configuration, processor 104 can be any kind of processing, including but not limited to: microprocessor
(μ P), microcontroller (μ C), digital information processor (DSP) or any combination of them.Processor 104 may include such as
The cache of one or more rank of on-chip cache 110 and second level cache 112 etc, processor core
114 and register 116.Exemplary processor core 114 may include arithmetic and logical unit (ALU), floating-point unit (FPU),
Digital signal processing core (DSP core) or any combination of them.Exemplary Memory Controller 118 can be with processor
104 are used together, or in some implementations, and Memory Controller 118 can be an interior section of processor 104.
Depending on desired configuration, system storage 106 can be any type of memory, including but not limited to: easily
The property lost memory (RAM), nonvolatile memory (ROM, flash memory etc.) or any combination of them.System storage
Device 106 may include operating system 120, one or more is using 122 and program data 124.In some embodiments,
It may be arranged to be executed instruction by one or more processors 104 using program data 124 on an operating system using 122.
Calculating equipment 100 can also include facilitating from various interface equipments (for example, output equipment 142, Peripheral Interface
144 and communication equipment 146) to basic configuration 102 via the communication of bus/interface controller 130 interface bus 140.Example
Output equipment 142 include graphics processing unit 148 and audio treatment unit 150.They can be configured as facilitate via
One or more port A/V 152 is communicated with the various external equipments of such as display or loudspeaker etc.Outside example
If interface 144 may include serial interface controller 154 and parallel interface controller 156, they, which can be configured as, facilitates
Via one or more port I/O 158 and such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment) or the external equipment of other peripheral hardwares (such as printer, scanner etc.) etc communicated.Exemplary communication is set
Standby 146 may include network controller 160, can be arranged to convenient for via one or more communication port 164 and one
A or multiple other calculate communication of the equipment 162 by network communication link.
Network communication link can be an example of communication media.Communication media can be usually presented as in such as carrier wave
Or computer readable instructions, data structure, program module in the modulated data signal of other transmission mechanisms etc, and can
To include any information delivery media." modulated data signal " can be such signal, one in its data set or
It is multiple or it change can the mode of encoded information in the signal carry out.As unrestricted example, communication media can
To include the wired medium of such as cable network or private line network etc, and it is such as sound, radio frequency (RF), microwave, infrared
(IR) the various wireless mediums or including other wireless mediums.Term computer-readable medium used herein may include depositing
Both storage media and communication media.
Calculate equipment 100 can be implemented as include desktop computer and notebook computer configuration personal computer,
It can be implemented as a part of portable (or mobile) electronic equipment of small size, these electronic equipments can be such as honeycomb electricity
Words, personal digital assistant (PDA), personal media player device, wireless network browsing apparatus, personal helmet, using special
With equipment or may include any of the above function mixing apparatus.It calculates equipment 100 and is also implemented as server, such as
File server, database server, apps server and WEB server etc..
In some embodiments, equipment 100 is calculated to be configured as executing the iris image of embodiment according to the present invention
Quality evaluating method 300.Wherein, the one or more application 122 for calculating equipment 100 includes for executing rainbow according to the present invention
The instruction of the quality evaluating method 300 of film image.
As it was noted above, the quality of acquisition iris image directly affects and identifies whether success.In some embodiments
In, the factor for influencing iris image quality (that is, clarity of iris image) mainly has: defocus mould caused by focusing inaccuracy
Paste, mobile caused motion blur, eyelid and eyelashes etc. are caused fuzzy etc. to blocking for iris region.In following side
In method 300, mainly for the defocus blur and motion blur of iris image, Lai Jinhang image quality evaluation.
In addition, it has been found that in iris authentication system, the eye figure of reference object usually under near-infrared irradiation
Picture, in this way, near-infrared irradiation light can form hot spot on pupil or iris.For identical equipment under same environmental conditions institute
The iris image of acquisition, the hot spot in image will not change because of the individual difference of subject.Also, motion blur and from
The fuzzy change that can correspond to certain hot spot form of coke.Such as Fig. 2A -2C, difference according to an embodiment of the invention is shown
The comparison diagram of the iris image of readability.Hot spot is indicated with the dot of white in figure.Wherein, Fig. 2A is clearly iris figure
Picture, Fig. 2 B and Fig. 2 C are fuzzy iris image, also, the vague category identifier of Fig. 2 B and Fig. 2 C it is different (Fig. 2 B belongs to motion blur,
Fig. 2 C belongs to defocus blur).Comparison diagram 2A- Fig. 2 C can be seen that (Fig. 2A can regard as without fuzzy for different vague category identifiers
Type) iris image, it includes hot spot have significant difference.
Fig. 3 shows the flow chart of the quality evaluating method 300 of iris image according to some embodiments of the invention.
As shown in figure 3, this method 300 starts from step S310.In step s310, iris image is acquired, and extracts the rainbow
The hot spot marginal point of film image.
According to an embodiment of the present, to improve arithmetic speed, before the hot spot marginal point for extracting iris image,
It further comprises the steps of: and original iris image (that is, iris image collected) is compressed and is filtered.Optionally, when
The pixel number of original iris image is greater than maximum pixel number, and (in one embodiment, maximum pixel number takes 60000, but is not limited to
This, can be adjusted according to application scenarios and demand) when, just original iris image is compressed, obtains compressed image.
Then, compressed image is filtered, typical compression method such as mean value is compressed, and typical filtering method such as Gauss filters
Wave, but the embodiment of the present invention is without limitation, any known or following known compression of images and filtering method, can be with
It is combined with the embodiment of the present invention, with implementation method 300.
Then, to the iris image after compression and filtering processing carry out following four steps processing (it is to be appreciated that if
It is that following four steps directly then are carried out to original iris image it is not necessary that original iris image is compressed and is filtered
Rapid processing, for convenient for statement, collectively referred to hereinafter as iris image), to extract glossing up marginal point.
The first step calculates the gradient of iris image.
According to a kind of embodiment, for each pixel in iris image, it is calculated in the x direction and the y direction (that is, water
Square to and vertical direction) on gradient value, then obtain the gradient of the pixel.All pixels are traversed, rainbow has just been obtained
The gradient of film image.Various gradient operators can be used for the calculating of image gradient, such as Sobel operator, Robert operator, drawn
General Laplacian operater etc..
The gradient according to an embodiment of the invention for calculating pixel (i, j) in iris image described below
The formula of pGradient (i, j), wherein GradV and GradH respectively indicates the ladder of pixel (i, j) in the x-direction and the z-direction
Angle value.
GradV=img (i-1, j-1)+img (i-1, j) * 2+img (i-1, j+1)-img (i+1, j-1)
-img(i+1,j)*2-img(i+1,j+1)
GradH=img (i-1, j-1)+img (i, j-1) * 2+img (i+1, j-1)-img (i-1, j+1)
-img(i,j+1)*2-img(i+1,j+1)
Second step extracts the marginal point in iris image according to the counted gradient of institute.
According to an embodiment of the invention, in this step, by the local direction for calculating edge in estimation iris image
(that is, direction of gradient), then finds the maximum value of partial gradient value using gradient direction, and the side of iris image is determined with this
Edge point.The detailed process according to an embodiment of the invention for executing this step is given below.
Firstly, calculating each pixel in iris image according to the gradient value of each pixel calculated in previous step
Gradient direction.Specifically, the gradient value according to each pixel in the x-direction and the z-direction, calculates the gradient side of the pixel
To.In one embodiment, the gradient direction pGradOritation of pixel (i, j) can be calculated according to the following formula
(i, j):
Then, based on the gradient direction of pixel, the greatest gradient of the pixel is determined.In a reality according to the present invention
It applies in example, the gradient direction of pixel is divided into 4 sections, when which section the gradient direction of pixel belong to, just press
The greatest gradient of the pixel is calculated according to the mode in the section.For example, the maximum ladder of pixel (i, j) is calculated as follows
Spend MAXGrad.
In above formula, maxGradTH is configuration parameter, and optionally, value is set as 100.Function max (a, b, c) expression takes a,
Maximum value in b, c three.
Finally, the greatest gradient based on pixel, extracts the marginal point of iris image.
In one embodiment, the size relation of the gradient value of the greatest gradient based on pixel and the pixel is come true
Whether the fixed pixel is marginal point.Specifically, if the gradient value of pixel is greater than the greatest gradient of the pixel, it is determined that should
Pixel is marginal point；If the gradient value of pixel is not more than the greatest gradient of the pixel, it is determined that the pixel is not side
Edge point.It is alternatively possible to according to the size relation of above-mentioned greatest gradient and gradient value, binary map is generated, is extracted to characterize
Marginal point.The process for generating binary map can be indicated by following formula:
In above formula, pGradMask (i, j) is the pixel value of pixel (i, j) in binary map, and pGradient (i, j) is
The gradient value of pixel (i, j), MAXGrad are the greatest gradient of pixel (i, j).
So far, extracted marginal point just contains the pixel on the profiles such as eyes, iris, hot spot.In the case where connecing
In the third step come, according to the grey scale change of extracted marginal point, candidate marginal is selected from marginal point.
According to a kind of embodiment, the grey scale change of marginal point four direction is first calculated；Determine the absolute value of grey scale change most
Big direction；On the direction of maximum absolute value, candidate marginal is determined from marginal point.
It is further elaborated especially by following formula.
If the coordinate of marginal point is (i, j), iris image is denoted as small_img, with small_img (i, j) representative edge
The gray value of edge point (i, j) calculates each marginal point in iris image and becomes in the gray scale of four direction according to such as next group of formula
Change, be denoted as a, b, c, d respectively:
A=small_img (i-1, j-1)-small_img (i+1, j+1)
B=small_img (i, j-1)-small_img (i, j+1)
C=small_img (i-1, j+1)-small_img (i+1, j-1)
D=small_img (i-1, j)-small_img (i+1, j)
A, b, c are calculated separately, the absolute value of d is denoted as respectively: abs (a), abs (b), abs (c), abs (d).Determine this
The value of maximum absolute value in 4 absolute values is denoted as max, and determines the corresponding direction (serial number N) of max.For example, if max=
Abs (a), then N=1；If max=abs (b), N=2；If max=abs (c), N=3；If max=abs (d), N=4.
If marginal point (i, j) is hot spot marginal point, the point on the direction of the maximum absolute value of grey scale change, in hot spot
Pixel value is big, and the point pixel value outside hot spot is small.Accordingly, if on the direction of maximum absolute value, two of the two sides marginal point (i, j)
Pixel is big or small simultaneously simultaneously, it is determined that the marginal point is not hot spot marginal point.That is, in the side of maximum absolute value
Upwards, candidate marginal is determined from marginal point.
Continue example as above, calculates the mean value of the gray value of all pixels point in iris image, be denoted as meanimg.For every
A marginal point (i, j), determines whether it is candidate marginal according to following process.
If N=1, when marginal point (i, j) meets following conditions, determine that marginal point (i, j) is candidate marginal:
Small_img (i-1, j-1)<meanimgandsmall_img ( i+1,j+1 )>meanimg, or
Small_img (i-1, j-1)>meanimg and small_img (i+1, j+1)<meanimg.
If N=2, when marginal point (i, j) meets following conditions, determine that marginal point (i, j) is candidate marginal:
Small_img (i, j-1)<meanimgandsmall_img ( i,j+1 )>meanimg, or
Small_img (i, j-1)>meanimg and small_img (i, j+1)<meanimg.
If N=3, when marginal point (i, j) meets following conditions, determine that marginal point (i, j) is candidate marginal:
Small_img (i-1, j+1)<meanimgandsmall_img ( i+1,j-1 )>meanimg, or
Small_img (i-1, j+1)>meanimg and small_img (i+1, j-1)<meanimg.
If N=4, when marginal point (i, j) meets following conditions, determine that marginal point (i, j) is candidate marginal:
Small_img (i-1, j)<meanimgandsmall_img ( i+1,j )>meanimg, or
Small_img (i-1, j)>meanimg and small_img (i+1, j)<meanimg.
4th step screens glossing up marginal point according to the coordinate of candidate marginal from candidate marginal.
The process of screening hot spot marginal point according to an embodiment of the present invention described below.
(1) by calculating the average value of the coordinate of all candidate marginals, center point coordinate is generated.
If the coordinate of candidate marginal is (xi,yi), i=1,2...n, wherein n indicates the number of candidate marginal, then,
The average value of the coordinate of candidate marginal can be calculated by following formula:
That is, center point coordinate is (meanX, meanY).
(2) pass through the distance value D of calculating each candidate marginal and central pointi, the average value of all distance values is generated, as
Apart from mean value meanD.
D can be calculated by following formulai:
In above formula, (xi,yi) indicate candidate marginal coordinate, (meanX, meanY) indicate center point coordinate.
(3) by the way that selected distance value is no more than the marginal point apart from mean value from candidate marginal, to determine new candidate
Marginal point.That is, deleting D from candidate marginaliThe point of > meanD, using candidate marginal remaining after deletion as new time
Select marginal point.
(4) by calculating the variance of the distance value of new candidate marginal, to determine glossing up marginal point.
About the calculating of variance, details are not described herein again, and the variance of the distance value of new candidate marginal is denoted as stdD.
If variance stdD be less than predetermined value (optionally, predetermined value takes 3, but not limited to this, can rule of thumb and application scenarios
The suitable value of setting), then using new candidate marginal as hot spot marginal point.
If variance stdD is not less than predetermined value, to new candidate marginal, repeat above-mentioned generation center point coordinate and away from
The step of from mean value and determining new candidate marginal and calculating variance (that is, (1)~(4) that repeat the above steps), Zhi Daosuo
Counted variance is less than predetermined value, using identified new candidate marginal as hot spot marginal point.
In another embodiment, can also repeat the above steps (1)~(3), until the quantity of new candidate marginal
Until no longer reducing, will it is final determined by new candidate marginal as hot spot marginal point.
Such as Fig. 4 A and Fig. 4 B, respectively illustrate according to an embodiment of the invention comprising candidate marginal and comprising hot spot
The iris image of marginal point.As can be seen that in Figure 4 A, most of candidate marginal is the wheel on the hot spot in pupil center
Wide, there are also small part candidate marginals to be scattered on sclera (canthus part in such as Fig. 4 A)；And in figure 4b, it is scattered in sclera
On marginal point it is deleted.
Then, in step s 320, ellipse fitting is carried out to hot spot marginal point, to obtain the ellipse of at least one fitting.
The basic ideas of ellipse fitting are: for giving one group of sample point in plane, finding an ellipse, it is made to the greatest extent may be used
It can be close to these sample points.Specific method about ellipse fitting is not developed in details herein, and those skilled in the art can be used
Such as the methods of least square method to carry out ellipse fitting to hot spot marginal point.
In one embodiment, according to the connected relation of hot spot marginal point, hot spot marginal point is divided into two hot spots.About
Connected relation between pixel can be described by pixel path.Assuming that being the pixel of (x, y) from coordinate in set of pixels T
P is to the access for the pixel q that coordinate is (s, t), and the sequence being made of a series of specific pixel, coordinate is successively are as follows: (x,
Y), (x1, y1) ..., (s, t), and two adjacent pixels are adjacent.In this case, just from pixel p to pixel q
Form a pixel path.If there was only a pixel path in set of pixels T, then, pixel p is exactly to be connected in S with q.
Generally, hot spot marginal point can be divided into two hot spots in left and right.
Then, the two hot spots are fitted to ellipse respectively.The ellipse that fitting obtains is denoted as: Ax2+Bxy+Cy2+Dx+Ey
+ F=0.
As Fig. 5 shows the partial schematic diagram according to an embodiment of the invention for fitting elliptical iris image.Fig. 5
In, two white border circular areas indicate hot spots, and what is depicted in hot spot with black curve is exactly that the two hot spots are corresponding
The ellipse of fitting.
Then, in step S330, oval according to fitting calculates fitting parameter.In an embodiment according to the present invention,
Fitting parameter includes: the distance between each elliptical area, eccentricity and two ellipses.It is described below to calculate above-mentioned fitting ginseng
Several processes.
Continue the general expression of elliptic equation as described above: Ax2+Bxy+Cy2+ Dx+Ey+F=0 can be represented ellipse
Round geometric center XcAnd Yc:
In this way, elliptical major semiaxis a and semi-minor axis b can be calculated separately out as follows:
Then, so that it may calculate elliptical area S:
S=π ab
Further calculate out elliptical eccentricity e:
Above-mentioned calculating is carried out to two ellipses fitted respectively, two elliptical areas is acquired respectively and (is denoted as S1 respectively
And S2) and eccentricity (being denoted as e1 and e2 respectively).
In addition, two elliptical geometric centers of connection calculate between geometric center with two oval formation, 4 intersection points
Two intersection points distance, as the two elliptical distance DIS.
Then in step S340, it is based on above-mentioned fitting parameter, determines the quality evaluation result of iris image.
In one embodiment, according to each elliptical area, determine area and.That is, by two elliptical faces
Product is added, and obtains area and Ssum=S1+S2.When the fitting parameter acquired in iris image while when meeting following condition, really
The fixed iris image is clear image: area and SsumIn the first predetermined interval and each elliptical eccentricity e1 and e2 locates
Third predetermined interval is in the distance between the second predetermined interval and two ellipses DIS.In embodiment according to the present invention
In, the first predetermined interval is set as [Smin_th,Smax_th], the second predetermined interval is set as (0, eth], third predetermined interval is set as
[DISth,+∞)。
In addition, if area and SsumIt is not at the first predetermined interval, it is determined that the iris image is the first vague category identifier.?
In the embodiment of the present invention, the first vague category identifier is defocus blur.Further, if area and Ssum< Smin_th, it is determined that
The iris image is remote defocus blur；If area and Ssum> Smax_th, it is determined that the iris image is nearly defocus blur.Wherein,
Smin_thAnd Smax_thFor empirical value, when size and acquisition iris image with iris image the illumination of used near-infrared lamp it is big
It is small related.
If each elliptical eccentricity e1 and e2 is not at the second predetermined interval, it is determined that the iris image is the second mould
Paste type.In an embodiment of the present invention, the second vague category identifier is motion blur.Wherein, ethIt is empirical value (according to the present invention
One embodiment in, ethIt takes 0.5), it is related with the shape of near-infrared lamp used when acquisition iris image and disposing way.
If the distance between two ellipses DIS is not at third predetermined interval, it is determined that the iris image is first fuzzy
Type or the second vague category identifier.Further, iris image may be close burnt fuzzy at this time, it is also possible to motion blur.
For the relationship between each fitting parameter of comparative illustration and the quality of iris image, table 1 shows real according to the present invention
Apply the relationship between the fitting parameter of example and picture quality.
The relationship of table 1 fitting parameter and picture quality
The quality assessment scheme of iris image according to the present invention, by extracting the hot spot of iris image and being carried out to it
Analysis, obtains the quality evaluation result about iris image.Since hot spot will not change because of the individual difference of subject,
Therefore the misjudgment introduced due to the iris texture difference of Different Individual can be got rid of according to the solution of the present invention.
In addition, according to the solution of the present invention, providing the corresponding relationship of a kind of elliptical fitting parameter and picture quality.Needle
It, can be by adjusting the threshold value in the first, second, third predetermined interval (that is, S to different iris capturing systemsmin_th,
Smax_th,eth,DISth), to be applicable in different application scenarios (for example, by adjusting according to the illumination size of near-infrared lamp
Smin_thAnd Smax_thValue).It is also possible to adjust the Stringency of image quality evaluation by adjusting above-mentioned threshold value.
Various technologies described herein are realized together in combination with hardware or software or their combination.To the present invention
Method and apparatus or the process and apparatus of the present invention some aspects or part can take insertion tangible media, such as can
Program code (instructing) in mobile hard disk, USB flash disk, floppy disk, CD-ROM or other any machine readable storage mediums
Form, wherein when program is loaded into the machine of such as computer etc, and when being executed by the machine, the machine becomes to practice
Equipment of the invention.
In the case where program code executes on programmable computers, calculates equipment and generally comprise processor, processor
Readable storage medium (including volatile and non-volatile memory and or memory element), at least one input unit, and extremely
A few output device.Wherein, memory is configured for storage program code；Processor is configured for according to the memory
Instruction in the said program code of middle storage executes method of the invention.
By way of example and not limitation, readable medium includes readable storage medium storing program for executing and communication media.Readable storage medium storing program for executing
Store the information such as computer readable instructions, data structure, program module or other data.Communication media is generally such as to carry
The modulated message signals such as wave or other transmission mechanisms embody computer readable instructions, data structure, program module or other
Data, and including any information transmitting medium.Above any combination is also included within the scope of readable medium.
In the instructions provided here, algorithm and display not with any certain computer, virtual system or other
Equipment is inherently related.Various general-purpose systems can also be used together with example of the invention.As described above, it constructs this kind of
Structure required by system is obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can
With using various programming languages realize summary of the invention described herein, and the description that language-specific is done above be for
Disclosure preferred forms of the invention.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, knot is not been shown in detail
Structure and technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims than feature more features expressly recited in each claim.More precisely, as following
As claims reflect, inventive aspect is all features less than single embodiment disclosed above.Therefore, it abides by
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
As a separate embodiment of the present invention.
Those skilled in the art should understand that the module of the equipment in example disclosed herein or unit or groups
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in the example
In different one or more equipment.Module in aforementioned exemplary can be combined into a module or furthermore be segmented into multiple
Submodule.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
The present invention discloses together:
A9, the method as described in A8, wherein fitting parameter include: each elliptical area, eccentricity and two ellipses it
Between distance.A10, the method as described in A9, wherein be based on fitting parameter, determine the step of the quality evaluation result of iris image
Suddenly include: according to each elliptical area, determine area and；If area and in the first predetermined interval and it is each it is elliptical from
Heart rate is in the distance between the second predetermined interval and two ellipses and is in third predetermined interval, it is determined that iris image is
Clear image.A11, the method as described in A10, wherein be based on fitting parameter, determine the step of the quality evaluation result of iris image
Suddenly further include: if area and being not at the first predetermined interval, it is determined that iris image is the first vague category identifier；If each elliptical
Eccentricity is not at the second predetermined interval, it is determined that iris image is the second vague category identifier；If the distance between two ellipses
It is not at third predetermined interval, it is determined that iris image is the first vague category identifier or the second vague category identifier.A12, as described in A11
Method, wherein the first vague category identifier is defocus blur, and the second vague category identifier is motion blur.A13, such as any one of A1-12 institute
The method stated, wherein before the step of extracting the hot spot marginal point of iris image, further comprise the steps of: to original iris figure
As being compressed and being filtered.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
In addition, be described as herein can be by the processor of computer system or by executing by some in the embodiment
The combination of method or method element that other devices of the function are implemented.Therefore, have for implementing the method or method
The processor of the necessary instruction of element forms the device for implementing this method or method element.In addition, Installation practice
Element described in this is the example of following device: the device be used for implement as in order to implement the purpose of the invention element performed by
Function.
As used in this, unless specifically stated, come using ordinal number " first ", " second ", " third " etc.
Description plain objects, which are merely representative of, is related to the different instances of similar object, and is not intended to imply that the object being described in this way must
Must have the time it is upper, spatially, sequence aspect or given sequence in any other manner.
Although the embodiment according to limited quantity describes the present invention, above description, the art are benefited from
It is interior it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.Additionally, it should be noted that
Language used in this specification primarily to readable and introduction purpose and select, rather than in order to explain or limit
Determine subject of the present invention and selects.Therefore, without departing from the scope and spirit of the appended claims, for this
Many modifications and changes are obvious for the those of ordinary skill of technical field.For the scope of the present invention, to this
It invents done disclosure to be illustrative and be not restrictive, it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. a kind of quality evaluating method of iris image, comprising steps of
Extract the hot spot marginal point of iris image；
Ellipse fitting is carried out to the hot spot marginal point, to obtain the ellipse of at least one fitting；
Oval according to fitting calculates fitting parameter；
Based on the fitting parameter, the quality evaluation result of the iris image is determined.
2. the method for claim 1, wherein the step of hot spot marginal point for extracting iris image includes:
Calculate the gradient of the iris image；
According to the counted gradient of institute, the marginal point in the iris image is extracted；
According to the grey scale change of extracted marginal point, candidate marginal is selected from the marginal point；
According to the coordinate of the candidate marginal, glossing up marginal point is screened from the candidate marginal.
3. method according to claim 2, wherein it is described according to the counted gradient of institute, extract the marginal point of iris image
Step includes:
Calculate the gradient direction of each pixel in iris image；
Gradient direction based on pixel determines the greatest gradient of the pixel；
Greatest gradient based on pixel extracts the marginal point of iris image.
4. method as claimed in claim 3, wherein the greatest gradient based on pixel extracts the edge of iris image
Point the step of include:
If the gradient value of pixel is greater than the greatest gradient of the pixel, it is determined that the pixel is marginal point；
If the gradient value of pixel is not more than the greatest gradient of the pixel, it is determined that the pixel is not marginal point.
5. the method as described in any one of claim 2-4, wherein the grey scale change according to extracted marginal point,
The step of candidate marginal is selected from marginal point include:
Calculate the grey scale change of the marginal point four direction；
Determine the direction of the maximum absolute value of grey scale change；
On the direction of the maximum absolute value, candidate marginal is determined from marginal point.
6. the method as described in any one of claim 2-5, wherein the coordinate according to candidate marginal, from candidate side
The step of screening glossing up marginal point, includes: in edge point
By calculating the average value of the coordinate of all candidate marginals, center point coordinate is generated；
By calculating the distance value of each candidate marginal and central point, the average value of all distance values is generated, as apart from mean value；
By the way that selected distance value is no more than the marginal point apart from mean value from candidate marginal, to determine new candidate marginal；
By calculating the variance of the distance value of new candidate marginal, to determine glossing up marginal point.
7. method as claimed in claim 6, wherein the variance by calculating the distance value of new candidate marginal is come
The step of determining glossing up marginal point include:
If the variance is less than predetermined value, using new candidate marginal as hot spot marginal point；
If the variance is not less than predetermined value, to new candidate marginal, the generation center point coordinate is repeated and apart from equal
Value and the step of determine new candidate marginal and calculate variance will be determined until the counted variance of institute is less than predetermined value
New candidate marginal as hot spot marginal point.
8. such as method of any of claims 1-7, wherein it is described that ellipse fitting is carried out to hot spot marginal point, with
Oval step at least one fitting includes:
According to the connected relation of hot spot marginal point, the hot spot marginal point is divided into two hot spots；
Described two hot spots are fitted to ellipse respectively.
9. a kind of calculating equipment, comprising:
One or more processors；
Memory；And
One or more programs, wherein one or more of programs are stored in the memory and are configured as by described one
A or multiple processors execute, and one or more of programs include for executing in method according to claims 1-8
The instruction of either method.
10. a kind of computer readable storage medium for storing one or more programs, one or more of programs include instruction,
Described instruction is when calculating equipment execution, so that the calculating equipment executes any in method according to claims 1-8
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910299773.7A CN110084789B (en) | 2019-04-15 | 2019-04-15 | Quality evaluation method of iris image and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910299773.7A CN110084789B (en) | 2019-04-15 | 2019-04-15 | Quality evaluation method of iris image and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110084789A true CN110084789A (en) | 2019-08-02 |
| CN110084789B CN110084789B (en) | 2021-11-09 |
Family
ID=67415018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910299773.7A Active CN110084789B (en) | 2019-04-15 | 2019-04-15 | Quality evaluation method of iris image and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084789B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705401A (en) * | 2019-09-19 | 2020-01-17 | 武汉虹识技术有限公司 | Iris collecting and identifying device and method |
| CN111476808A (en) * | 2020-03-19 | 2020-07-31 | 北京万里红科技股份有限公司 | Iris image definition evaluation method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359365A (en) * | 2008-08-07 | 2009-02-04 | 电子科技大学中山学院 | Iris positioning method based on Maximum between-Cluster Variance and gray scale information |
| CN102902970A (en) * | 2011-12-16 | 2013-01-30 | 北京天诚盛业科技有限公司 | Iris location method |
| US20140219516A1 (en) * | 2013-02-07 | 2014-08-07 | Ittiam Systems (P) Ltd. | System and method for iris detection in digital images |
-
2019
- 2019-04-15 CN CN201910299773.7A patent/CN110084789B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359365A (en) * | 2008-08-07 | 2009-02-04 | 电子科技大学中山学院 | Iris positioning method based on Maximum between-Cluster Variance and gray scale information |
| CN102902970A (en) * | 2011-12-16 | 2013-01-30 | 北京天诚盛业科技有限公司 | Iris location method |
| US20140219516A1 (en) * | 2013-02-07 | 2014-08-07 | Ittiam Systems (P) Ltd. | System and method for iris detection in digital images |
Non-Patent Citations (3)
| Title |
|---|
| 徐海颖: "《虹膜图像的质量评价及自采集的研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王琪: "《虹膜识别中的若干关键问题研究》", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 王琪等: "《基于椭圆拟合的晃动虹膜图像的检测算法》", 《东北大学学报（自然科学版）》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705401A (en) * | 2019-09-19 | 2020-01-17 | 武汉虹识技术有限公司 | Iris collecting and identifying device and method |
| CN111476808A (en) * | 2020-03-19 | 2020-07-31 | 北京万里红科技股份有限公司 | Iris image definition evaluation method and device |
| CN111476808B (en) * | 2020-03-19 | 2023-12-26 | 北京万里红科技有限公司 | Iris image definition evaluation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110084789B (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6778247B2 (en) | Image and feature quality for eye blood vessels and face recognition, image enhancement and feature extraction, and fusion of eye blood vessels with facial and / or subface regions for biometric systems | |
| CN105917353B (en) | Feature extraction and matching for biological identification and template renewal | |
| CN110162567B (en) | Two-dimensional scalar field data visualization method and system based on color table optimization | |
| CN110163078A (en) | The service system of biopsy method, device and application biopsy method | |
| WO2005109344A1 (en) | Method for registering iris, device for registering iris and program for registering iris | |
| CN106056064A (en) | Face recognition method and face recognition device | |
| CN108416343B (en) | Face image recognition method and device | |
| CN105631417A (en) | Video beautification system and method applied to Internet video live broadcast | |
| CN105335719A (en) | Living body detection method and device | |
| CN108765264B (en) | Image beautifying method, device, equipment and storage medium | |
| CN109871845A (en) | Certificate image extracting method and terminal device | |
| CN109584153A (en) | Modify the methods, devices and systems of eye | |
| CN111062891A (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN109859217A (en) | The dividing method in pore region and calculating equipment in facial image | |
| CN110084789A (en) | A kind of quality evaluating method and calculating equipment of iris image | |
| CN110189341A (en) | A kind of method, the method and device of image segmentation of Image Segmentation Model training | |
| CN109299634A (en) | Spot detection method, system, equipment and storage medium | |
| Chidananda et al. | Entropy-cum-Hough-transform-based ear detection using ellipsoid particle swarm optimization | |
| CN109815823A (en) | Data processing method and Related product | |
| Sharma et al. | Image recognition system using geometric matching and contour detection | |
| CN117496019B (en) | Image animation processing method and system for driving static image | |
| Ramenahalli et al. | Local spectral anisotropy is a valid cue for figure–ground organization in natural scenes | |
| Lin et al. | Multi-scale contour detection model based on fixational eye movement mechanism | |
| JP7360217B2 (en) | Method for obtaining data from an image of an object of a user having biometric characteristics of the user | |
| KR102634186B1 (en) | Method for verifying the identity of a user by identifying an object by identifying an object in an image containing the user's biometric characteristics and isolating the part of the image containing the biometric characteristics from other parts of the image within an image that has a biometric characteristic of the user and separating a portion of the image comprising the biometric characteristic from other portions of the image) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230826 Address after: No. 8, Row 9, Fatou Dongli Middle Yard, Chaoyang District, Beijing, 100020 Patentee after: Wang Xiaopeng Address before: 541000 building D2, HUTANG headquarters economic Park, Guimo Avenue, Qixing District, Guilin City, Guangxi Zhuang Autonomous Region Patentee before: Guangxi Code Interpretation Intelligent Information Technology Co.,Ltd. |